Most existing knowledge graph completion methods fail to model the fine-grained interactions among elements within triples, such as dependencies between entity attributes or contextual relationships involving predicates and entities. This limitation weakens their ability to infer implicit knowledge and hinders overall reasoning performance. To address this issue, we define a three-level classification of element interactions: Interactions between Elements at the Head Entity (IEH), Interactions between Elements at the Relationship (IER), and Interactions between Elements at the Tail Entity (IET), that systematically models the influence propagation patterns among knowledge graph triples at element level. Based on these interaction types, we propose a novel Knowledge Graph Completion Model Based on Fine-Grained Element Interactions (EI-KGC). Our model captures both global structural patterns and semantic dependencies within triples by combining GNN propagation with fine-grained interaction modeling. Experimental results show that the EI-KGC consistently outperforms traditional baseline models, demonstrating the high effectiveness of our proposed model.

The goal of document-level relation extraction is to extract semantic information from multiple sentences within a document and identify the relations between entities across sentences. However, effectively representing the document's content and reasoning about cross-sentence entities presents a formidable challenge. In this paper, we propose an efficient Document-Level Relation Extraction Model based on Heterogeneous Graph Reasoning (HGR-DREM), which enables relation extraction more accurate. Specifically, we first construct a document-level heterogeneous graph to comprehensively capture the semantic relations between entities. Then, we design a meta-path attention-based reasoning mechanism to enhance the mutual influence among graph nodes. Furthermore, we utilize an extended adjacency matrix to represent the heterogeneous graph and leverage graph convolutional neural networks (GCNs) to extract high-dimensional features. The experiments on a real-world dataset demonstrate the effectiveness of our proposed model. All codes have been released at https://github.com/NuyoaH-code/HGR-DREM.

Data imputation has increasingly gained attention due to its critical role in enhancing data quality and accuracy. However, traditional imputation methods often lack the ability to leverage the underlying category information and employ static denoising strategies, leading to suboptimal results. In this paper, we propose a novel data imputation method based on generative adversarial denoise network to predict and fill in the missing values. Our approach first employs a dataset partitioning scheme to divide the dataset into several subsets based on potential data categories. We then propose a Generative Adversarial Denoise Imputation Network (GAD IN) to combine dynamic noise reduction with generative adversarial networks to enhance the model's adaptability and robustness. Extensive experiments on real-world datasets validate the superior performance of our proposed method in comparison to existing techniques.

At present, event-based social network (EBSN) platforms are becoming more and more popular, which main function is to arrange appropriate social activities for interested users. The existing methods usually assume that each user can participate in a limited number of events and solve the spatio-temporal conflicts caused by the limited number of events. However, in practical applications, the existing methods emerge the following problems: (1) they don't estimate the time cost caused by travel distance; (2) the constraint of the limiting number of users participating events and the schedule of users is not accurate enough. Therefore, first, we combine the position information and propose RDP algorithm to provide personalized event planning based on considering the free time of users, the average moving speed of users, the interest value of users as a whole, which ensures the approximate ratio of our algorithm. Second, we present RGPV and the RGPT algorithms to reduce the running time and improve the efficiency of time and space, so as to ensure each user can participate in the events on time. Finally, the experiments based on the real dataset can show that the proposed algorithms are effective and efficient.

RFID technologies are applied extensively in Cyber-Physical Systems (CPS). RFID system collects, filters, and integrates large volume of events gathered continuously by readers to process composite event detections from applications. When the system processes many composite events, detection sharing is quite important for their execution and enhancing the performance of the system. In this paper, we propose a composite event detecting approach based on similar sub-event for RFID event streams. In order to achieve it, we propose the concept of small event by analyzing the different composite event and the relationship between operators, give the rules and properties of composite event rewriting, and give an approach of small event sharing and an implementation strategy for sharing similar sub-events. Finally, we demonstrate the effectiveness of our approach through a detail performance analysis of our algorithm implementation as well as through a comparison to a typical detection algorithm.

Smart Grid is an important application in Internet Of Things (IOT). Monitoring data in large-scale smart grid are massive, real-time and dynamic which collected by a lot of sensors, Intelligent Electronic Devices (IED) and etc.. All on account of that, traditional centralized storage proposals aren't applicable to data storage in large-scale smart grid. Therefore, we propose a data-centric storage approach in support of monitoring system in large-scale smart grid: Hierarchical Extended Storage Mechanism for Massive Dynamic Data (HES). HES stores monitoring data in different area according to data types. It can add storage nodes dynamically by coding method with extended hash function for avoiding data loss of incidents and frequent events. Monitoring data are stored dispersedly in the nodes of the same player by the multi-threshold levels means in HES, which avoids load skew. The simulation results show that HES satisfies the needs of massive dynamic data storage, and achieves load balance and a longer life cycle of monitoring network.